A study of image recognition system

This paper describes an image recognition system in which top-down and bottom-up approaches are integrated. The proposed system consists of a feature extractor and an interpreter. The feature extractor performs low level image processing in the first stage to obtain feature primitives. In the second stage, these primitives are grouped into feature candidates for a recognition, using the perceptional rule. The interpreter infers what the object is, using intrinsic features selected from the feature candidates and knowledge of the object. If some ambiguity exists, the interpreter builds up a hypothesis about the object and requests the extractor to verify it. This inference cycle of hypothesis and verification is repeated until the identification is completed. The effectiveness of this system is confirmed by experimentation